Triple

T1634085
Position Surface form Disambiguated ID Type / Status
Subject John L. Hennessy E35324 entity
Predicate familyName P18 FINISHED
Object Hennessy
Hennessy is a surname most prominently associated with John L. Hennessy, a renowned computer scientist and former president of Stanford University.
 E184205 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Hennessy | Statement: [John L. Hennessy, familyName, Hennessy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Hennessy
Context triple: [John L. Hennessy, familyName, Hennessy]
  • A. Ballantine
    Ballantine is the surname of the individual after whom the prestigious Stuart Ballantine Medal for scientific and engineering achievement is named.
  • B. Pernod Ricard
    Pernod Ricard is a major French wine and spirits company known globally for brands such as Absolut, Jameson, and Chivas Regal.
  • C. Bourbon-l’Archambault
    Bourbon-l’Archambault is a historic spa town in central France known as the ancestral seat of the Bourbon dynasty.
  • D. Chivas USA
    Chivas USA was a now-defunct Major League Soccer club based in the Los Angeles area that operated as a sister team to Mexico’s C.D. Guadalajara.
  • E. Blanc Fumé
    Blanc Fumé is an alternative name for Sauvignon Blanc, particularly associated with smoky, flinty-style expressions of the grape.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Hennessy
Triple: [John L. Hennessy, familyName, Hennessy]
Generated description
Hennessy is a surname most prominently associated with John L. Hennessy, a renowned computer scientist and former president of Stanford University.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Hennessy
Target entity description: Hennessy is a surname most prominently associated with John L. Hennessy, a renowned computer scientist and former president of Stanford University.
  • A. Ballantine
    Ballantine is the surname of the individual after whom the prestigious Stuart Ballantine Medal for scientific and engineering achievement is named.
  • B. Pernod Ricard
    Pernod Ricard is a major French wine and spirits company known globally for brands such as Absolut, Jameson, and Chivas Regal.
  • C. Bourbon-l’Archambault
    Bourbon-l’Archambault is a historic spa town in central France known as the ancestral seat of the Bourbon dynasty.
  • D. Chivas USA
    Chivas USA was a now-defunct Major League Soccer club based in the Los Angeles area that operated as a sister team to Mexico’s C.D. Guadalajara.
  • E. Blanc Fumé
    Blanc Fumé is an alternative name for Sauvignon Blanc, particularly associated with smoky, flinty-style expressions of the grape.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69a886036bc081909ff5de16dbe5e8ea completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a909f86abc8190b0b81310dcd7feed completed March 5, 2026, 4:43 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad58d9db5c819081408977834ad606 completed March 8, 2026, 11:09 a.m.
NEDg Description generation batch_69ad5a625d088190bbacbb69a0569d49 completed March 8, 2026, 11:15 a.m.
NED2 Entity disambiguation (via description) batch_69ad5ae605f88190b5e42d7cf923e9bb completed March 8, 2026, 11:17 a.m.
Created at: March 4, 2026, 7:28 p.m.